@mastra/mcp-docs-server 1.2.19-alpha.4 → 1.2.19

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (100) hide show
  1. package/.docs/docs/channels.md +28 -1
  2. package/.docs/docs/deployment/cloud-providers.md +1 -0
  3. package/.docs/docs/deployment/mastra-server.md +19 -0
  4. package/.docs/docs/deployment/overview.md +1 -0
  5. package/.docs/docs/deployment/workers.md +2 -2
  6. package/.docs/docs/harness/durable-agents.md +1 -1
  7. package/.docs/docs/mastra-platform/api.md +54 -0
  8. package/.docs/docs/mastra-platform/deploy.md +101 -0
  9. package/.docs/docs/mastra-platform/observability.md +3 -1
  10. package/.docs/docs/mastra-platform/server.md +6 -11
  11. package/.docs/docs/mastra-platform/studio.md +8 -10
  12. package/.docs/docs/memory/semantic-recall.md +19 -0
  13. package/.docs/docs/observability/feedback.md +14 -0
  14. package/.docs/docs/observability/integrations/exporters/mastra-storage.md +19 -14
  15. package/.docs/docs/observability/metrics/overview.md +31 -44
  16. package/.docs/docs/sandbox/overview.md +43 -0
  17. package/.docs/docs/server/middleware.md +30 -0
  18. package/.docs/docs/server/server-adapters.md +109 -34
  19. package/.docs/docs/storage.md +2 -0
  20. package/.docs/docs/subagents.md +6 -6
  21. package/.docs/integrations/channels/github.md +56 -9
  22. package/.docs/integrations/channels/imessage.md +150 -8
  23. package/.docs/integrations/databases/elasticsearch.md +156 -0
  24. package/.docs/integrations/databases/libsql.md +16 -0
  25. package/.docs/integrations/databases/mongodb.md +1 -1
  26. package/.docs/integrations/databases/postgresql.md +26 -0
  27. package/.docs/integrations/databases/valkey.md +99 -0
  28. package/.docs/integrations/deploy/kubernetes-helm.md +332 -0
  29. package/.docs/integrations/deploy/kubernetes.md +1 -1
  30. package/.docs/integrations/deploy/render.md +47 -61
  31. package/.docs/integrations/sandboxes/daytona.md +52 -0
  32. package/.docs/integrations/sandboxes/e2b-desktop.md +128 -0
  33. package/.docs/integrations/sandboxes/e2b.md +6 -0
  34. package/.docs/integrations/sandboxes/vercel.md +2 -2
  35. package/.docs/integrations/tools/parallel.md +240 -0
  36. package/.docs/integrations.md +5 -0
  37. package/.docs/models/environment-variables.md +9 -0
  38. package/.docs/models/gateways/netlify.md +12 -5
  39. package/.docs/models/gateways/openrouter.md +5 -10
  40. package/.docs/models/gateways/vercel.md +5 -5
  41. package/.docs/models/index.md +1 -1
  42. package/.docs/models/providers/agentrouter.md +17 -34
  43. package/.docs/models/providers/agnes.md +75 -0
  44. package/.docs/models/providers/aixy.md +73 -0
  45. package/.docs/models/providers/aki-io.md +14 -13
  46. package/.docs/models/providers/chutes.md +2 -2
  47. package/.docs/models/providers/cline-pass.md +4 -2
  48. package/.docs/models/providers/crof.md +3 -8
  49. package/.docs/models/providers/deepseek.md +4 -6
  50. package/.docs/models/providers/edenai.md +14 -14
  51. package/.docs/models/providers/evroc.md +3 -2
  52. package/.docs/models/providers/gmicloud.md +6 -4
  53. package/.docs/models/providers/huggingface.md +2 -1
  54. package/.docs/models/providers/hyper.md +5 -5
  55. package/.docs/models/providers/inceptron.md +2 -2
  56. package/.docs/models/providers/iteracompute.md +73 -0
  57. package/.docs/models/providers/kilo.md +26 -27
  58. package/.docs/models/providers/llmgateway-providers.md +18 -9
  59. package/.docs/models/providers/llmgateway.md +3 -5
  60. package/.docs/models/providers/llmtech.md +73 -0
  61. package/.docs/models/providers/nano-gpt.md +22 -13
  62. package/.docs/models/providers/neosmith.md +104 -0
  63. package/.docs/models/providers/nvidia.md +3 -1
  64. package/.docs/models/providers/ofox.md +2 -1
  65. package/.docs/models/providers/openai.md +2 -2
  66. package/.docs/models/providers/opencode-go.md +3 -2
  67. package/.docs/models/providers/opper.md +112 -0
  68. package/.docs/models/providers/pendra.md +78 -0
  69. package/.docs/models/providers/requesty.md +1 -1
  70. package/.docs/models/providers/standardcompute.md +73 -0
  71. package/.docs/models/providers/vivgrid.md +2 -1
  72. package/.docs/models/providers/wandb.md +2 -1
  73. package/.docs/models/providers/zai.md +2 -1
  74. package/.docs/models/providers.md +9 -0
  75. package/.docs/reference/agents/channels.md +1 -1
  76. package/.docs/reference/ai-sdk/handle-chat-stream.md +11 -0
  77. package/.docs/reference/ai-sdk/with-sse-heartbeat.md +47 -0
  78. package/.docs/reference/cli/mastra.md +10 -4
  79. package/.docs/reference/client-js/observability.md +1 -1
  80. package/.docs/reference/index.md +5 -0
  81. package/.docs/reference/observability/feedback.md +4 -0
  82. package/.docs/reference/observability/metrics/automatic-metrics.md +1 -1
  83. package/.docs/reference/observability/metrics/queries.md +462 -0
  84. package/.docs/reference/pubsub/valkey-streams.md +84 -0
  85. package/.docs/reference/rag/vector-databases.md +4 -4
  86. package/.docs/reference/server/elysia-adapter.md +184 -0
  87. package/.docs/reference/server/express-adapter.md +6 -8
  88. package/.docs/reference/server/hono-adapter.md +19 -6
  89. package/.docs/reference/storage/turso.md +88 -0
  90. package/.docs/reference/streaming/ChunkType.md +29 -1
  91. package/.docs/reference/streaming/agents/stream.md +1 -3
  92. package/.docs/reference/tools/mcp-client.md +41 -9
  93. package/.docs/reference/vectors/mongodb.md +11 -11
  94. package/.docs/reference/vectors/pg.md +2 -0
  95. package/.docs/reference/workspace/local-sandbox.md +2 -0
  96. package/.docs/reference/workspace/platform-sandbox.md +3 -1
  97. package/.docs/reference/workspace/sandbox.md +143 -3
  98. package/CHANGELOG.md +81 -0
  99. package/package.json +6 -6
  100. package/.docs/docs/observability/metrics/querying.md +0 -314
package/.docs/models/providers/evroc.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![evroc logo](https://models.dev/logos/evroc.svg)evroc
4
4
 
5
- Access 15 evroc models through Mastra's model router. Authentication is handled automatically using the `EVROC_API_KEY` environment variable.
5
+ Access 16 evroc models through Mastra's model router. Authentication is handled automatically using the `EVROC_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [evroc documentation](https://docs.evroc.com/products/think/overview.html).
8
8
 
@@ -49,7 +49,8 @@ for await (const chunk of stream) {
49
49
  | `evroc/openai/whisper-large-v3-turbo` | 448 | | | | | | $0.00 | $0.00 |
50
50
  | `evroc/Qwen/Qwen3-Embedding-8B` | 41K | | | | | | $0.12 | $0.12 |
51
51
  | `evroc/Qwen/Qwen3-Reranker-4B` | 32K | | | | | | $0.06 | — |
52
- | `evroc/Qwen/Qwen3.6-35B-A3B-FP8` | 262K | | | | | | $0.34 | $1 |
52
+ | `evroc/Qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.34 | $1 |
53
+ | `evroc/Qwen/Qwen3.8-27B` | 262K | | | | | | $0.87 | $4 |
53
54
  | `evroc/zai-org/GLM-5.2` | 524K | | | | | | $1 | $6 |
54
55
 
55
56
  ## Advanced configuration
package/.docs/models/providers/gmicloud.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![GMI Cloud logo](https://models.dev/logos/gmicloud.svg)GMI Cloud
4
4
 
5
- Access 13 GMI Cloud models through Mastra's model router. Authentication is handled automatically using the `GMICLOUD_API_KEY` environment variable.
5
+ Access 15 GMI Cloud models through Mastra's model router. Authentication is handled automatically using the `GMICLOUD_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [GMI Cloud documentation](https://docs.gmicloud.ai).
8
8
 
@@ -17,7 +17,7 @@ const agent = new Agent({
17
17
  id: "my-agent",
18
18
  name: "My Agent",
19
19
  instructions: "You are a helpful assistant",
20
- model: "gmicloud/Qwen/Qwen3.7-Max"
20
+ model: "gmicloud/MiniMaxAI/MiniMax-M2.7"
21
21
  });
22
22
 
23
23
  // Generate a response
@@ -42,6 +42,8 @@ for await (const chunk of stream) {
42
42
  | `gmicloud/anthropic/claude-sonnet-4.6` | 410K | | | | | | $3 | $15 |
43
43
  | `gmicloud/deepseek-ai/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.11 | $0.22 |
44
44
  | `gmicloud/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $1 | $3 |
45
+ | `gmicloud/MiniMaxAI/MiniMax-M2.7` | 197K | | | | | | $0.30 | $1 |
46
+ | `gmicloud/MiniMaxAI/MiniMax-M3` | 1.0M | | | | | | $0.60 | $2 |
45
47
  | `gmicloud/moonshotai/Kimi-K2.6` | 66K | | | | | | $0.85 | $4 |
46
48
  | `gmicloud/moonshotai/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
47
49
  | `gmicloud/openai/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
@@ -60,7 +62,7 @@ const agent = new Agent({
60
62
  name: "custom-agent",
61
63
  model: {
62
64
  url: "https://api.gmi-serving.com/v1",
63
- id: "gmicloud/Qwen/Qwen3.7-Max",
65
+ id: "gmicloud/MiniMaxAI/MiniMax-M2.7",
64
66
  apiKey: process.env.GMICLOUD_API_KEY,
65
67
  headers: {
66
68
  "X-Custom-Header": "value"
@@ -79,7 +81,7 @@ const agent = new Agent({
79
81
  const useAdvanced = requestContext.task === "complex";
80
82
  return useAdvanced
81
83
  ? "gmicloud/zai-org/GLM-5.2-FP8"
82
- : "gmicloud/Qwen/Qwen3.7-Max";
84
+ : "gmicloud/MiniMaxAI/MiniMax-M2.7";
83
85
  }
84
86
  });
85
87
  ```
package/.docs/models/providers/huggingface.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Hugging Face logo](https://models.dev/logos/huggingface.svg)Hugging Face
4
4
 
5
- Access 69 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
5
+ Access 70 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
6
6
 
7
7
  Learn more in the [Hugging Face documentation](https://huggingface.co).
8
8
 
@@ -87,6 +87,7 @@ for await (const chunk of stream) {
87
87
  | `huggingface/Qwen/Qwen3.6-27B` | 262K | | | | | | $0.47 | $3 |
88
88
  | `huggingface/Qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.15 | $0.95 |
89
89
  | `huggingface/Qwen/Qwen3.8-2.4T-A95B` | 262K | | | | | | $3 | $6 |
90
+ | `huggingface/Qwen/Qwen3.8-27B` | 262K | | | | | | $0.40 | $3 |
90
91
  | `huggingface/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.10 | $0.30 |
91
92
  | `huggingface/stepfun-ai/Step-3.7-Flash` | 262K | | | | | | $0.20 | $1 |
92
93
  | `huggingface/tencent/Hy3` | 262K | | | | | | $0.14 | $0.58 |
package/.docs/models/providers/hyper.md CHANGED
@@ -37,19 +37,19 @@ for await (const chunk of stream) {
37
37
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
38
  | ---------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
39
  | `hyper/deepseek-v4-flash` | 1.0M | | | | | | $0.20 | $0.40 |
40
- | `hyper/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.48 | $1 |
40
+ | `hyper/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
41
41
  | `hyper/deepseek-v4-pro` | 1.0M | | | | | | $2 | $5 |
42
42
  | `hyper/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
43
- | `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.11 | $0.41 |
43
+ | `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.12 | $0.42 |
44
44
  | `hyper/glm-5` | 203K | | | | | | $0.91 | $3 |
45
45
  | `hyper/glm-5.1` | 203K | | | | | | $1 | $4 |
46
46
  | `hyper/glm-5.2` | 1.0M | | | | | | $2 | $5 |
47
- | `hyper/gpt-oss-120b` | 131K | | | | | | $0.19 | $0.70 |
47
+ | `hyper/gpt-oss-120b` | 128K | | | | | | $0.19 | $0.70 |
48
48
  | `hyper/kimi-k2.5` | 262K | | | | | | $0.54 | $3 |
49
49
  | `hyper/kimi-k2.6` | 262K | | | | | | $1 | $4 |
50
- | `hyper/kimi-k2.7-code` | 256K | | | | | | $1 | $4 |
50
+ | `hyper/kimi-k2.7-code` | 262K | | | | | | $1 | $4 |
51
51
  | `hyper/kimi-k3` | 1.0M | | | | | | $3 | $16 |
52
- | `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.64 | $0.77 |
52
+ | `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.60 | $0.74 |
53
53
  | `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.27 | $0.90 |
54
54
  | `hyper/minimax-m2.7` | 262K | | | | | | $0.41 | $2 |
55
55
  | `hyper/minimax-m3` | 512K | | | | | | $0.33 | $1 |
package/.docs/models/providers/inceptron.md CHANGED
@@ -37,9 +37,9 @@ for await (const chunk of stream) {
37
37
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
38
  | ---------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
39
  | `inceptron/deepseek-ai/DeepSeek-V4-Flash-0731` | 1.0M | | | | | | $0.13 | $0.28 |
40
- | `inceptron/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.60 | $3 |
40
+ | `inceptron/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.57 | $3 |
41
41
  | `inceptron/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.67 | $3 |
42
- | `inceptron/zai-org/GLM-5.2` | 1.0M | | | | | | $0.75 | $3 |
42
+ | `inceptron/zai-org/GLM-5.2` | 1.0M | | | | | | $0.75 | $2 |
43
43
 
44
44
  ## Advanced configuration
45
45
 
package/.docs/models/providers/iteracompute.md ADDED
@@ -0,0 +1,73 @@
1
+ > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
2
+
3
+ # ![IteraCompute logo](https://models.dev/logos/iteracompute.svg)IteraCompute
4
+
5
+ Access 1 IteraCompute model through Mastra's model router. Authentication is handled automatically using the `ITERACOMPUTE_API_KEY` environment variable.
6
+
7
+ Learn more in the [IteraCompute documentation](https://iteracompute.com/docs.html).
8
+
9
+ ```bash
10
+ ITERACOMPUTE_API_KEY=your-api-key
11
+ ```
12
+
13
+ ```typescript
14
+ import { Agent } from "@mastra/core/agent";
15
+
16
+ const agent = new Agent({
17
+ id: "my-agent",
18
+ name: "My Agent",
19
+ instructions: "You are a helpful assistant",
20
+ model: "iteracompute/iteracompute/qwen3.8-27b"
21
+ });
22
+
23
+ // Generate a response
24
+ const response = await agent.generate("Hello!");
25
+
26
+ // Stream a response
27
+ const stream = await agent.stream("Tell me a story");
28
+ for await (const chunk of stream) {
29
+ console.log(chunk);
30
+ }
31
+ ```
32
+
33
+ > **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [IteraCompute documentation](https://iteracompute.com/docs.html) for details.
34
+
35
+ ## Models
36
+
37
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
+ | --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
+ | `iteracompute/iteracompute/qwen3.8-27b` | 262K | | | | | | $0.35 | $3 |
40
+
41
+ ## Advanced configuration
42
+
43
+ ### Custom headers
44
+
45
+ ```typescript
46
+ const agent = new Agent({
47
+ id: "custom-agent",
48
+ name: "custom-agent",
49
+ model: {
50
+ url: "https://api.iteracompute.com/v1",
51
+ id: "iteracompute/iteracompute/qwen3.8-27b",
52
+ apiKey: process.env.ITERACOMPUTE_API_KEY,
53
+ headers: {
54
+ "X-Custom-Header": "value"
55
+ }
56
+ }
57
+ });
58
+ ```
59
+
60
+ ### Dynamic model selection
61
+
62
+ ```typescript
63
+ const agent = new Agent({
64
+ id: "dynamic-agent",
65
+ name: "Dynamic Agent",
66
+ model: ({ requestContext }) => {
67
+ const useAdvanced = requestContext.task === "complex";
68
+ return useAdvanced
69
+ ? "iteracompute/iteracompute/qwen3.8-27b"
70
+ : "iteracompute/iteracompute/qwen3.8-27b";
71
+ }
72
+ });
73
+ ```
package/.docs/models/providers/kilo.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Kilo Gateway logo](https://models.dev/logos/kilo.svg)Kilo Gateway
4
4
 
5
- Access 366 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
5
+ Access 365 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Kilo Gateway documentation](https://kilo.ai).
8
8
 
@@ -40,10 +40,10 @@ for await (const chunk of stream) {
40
40
  | `kilo/~anthropic/claude-haiku-latest` | 200K | | | | | | $1 | $5 |
41
41
  | `kilo/~anthropic/claude-opus-latest` | 1.0M | | | | | | $5 | $25 |
42
42
  | `kilo/~anthropic/claude-sonnet-latest` | 1.0M | | | | | | $2 | $10 |
43
- | `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.07 | $0.18 |
43
+ | `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.03 | $0.07 |
44
44
  | `kilo/~google/gemini-flash-latest` | 1.0M | | | | | | $0.38 | $2 |
45
45
  | `kilo/~google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
46
- | `kilo/~moonshotai/kimi-latest` | 975K | | | | | | $3 | $13 |
46
+ | `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $3 | $13 |
47
47
  | `kilo/~openai/gpt-latest` | 1.1M | | | | | | $2 | $10 |
48
48
  | `kilo/~openai/gpt-mini-latest` | 400K | | | | | | $0.75 | $5 |
49
49
  | `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
@@ -94,7 +94,7 @@ for await (const chunk of stream) {
94
94
  | `kilo/cohere/north-mini-code:free` | 256K | | | | | | — | — |
95
95
  | `kilo/deepseek/deepseek-chat` | 128K | | | | | | $0.40 | $1 |
96
96
  | `kilo/deepseek/deepseek-chat-v3-0324` | 164K | | | | | | $0.27 | $1 |
97
- | `kilo/deepseek/deepseek-chat-v3.1` | 164K | | | | | | $0.27 | $1 |
97
+ | `kilo/deepseek/deepseek-chat-v3.1` | 161K | | | | | | $0.27 | $1 |
98
98
  | `kilo/deepseek/deepseek-r1` | 64K | | | | | | $0.70 | $3 |
99
99
  | `kilo/deepseek/deepseek-r1-0528` | 164K | | | | | | $0.70 | $3 |
100
100
  | `kilo/deepseek/deepseek-r1-distill-llama-70b` | 8K | | | | | | $0.80 | $0.80 |
@@ -102,7 +102,7 @@ for await (const chunk of stream) {
102
102
  | `kilo/deepseek/deepseek-v3.2` | 164K | | | | | | $0.27 | $0.40 |
103
103
  | `kilo/deepseek/deepseek-v3.2-exp` | 164K | | | | | | $0.27 | $0.41 |
104
104
  | `kilo/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
105
- | `kilo/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.14 | $0.28 |
105
+ | `kilo/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
106
106
  | `kilo/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.22 | $0.66 |
107
107
  | `kilo/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
108
108
  | `kilo/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
@@ -114,7 +114,7 @@ for await (const chunk of stream) {
114
114
  | `kilo/google/gemini-2.5-pro-preview` | 1.0M | | | | | | $1 | $10 |
115
115
  | `kilo/google/gemini-2.5-pro-preview-05-06` | 1.0M | | | | | | $1 | $10 |
116
116
  | `kilo/google/gemini-3-flash-preview` | 1.0M | | | | | | $0.50 | $3 |
117
- | `kilo/google/gemini-3-pro-image` | 66K | | | | | | $2 | $12 |
117
+ | `kilo/google/gemini-3-pro-image` | 131K | | | | | | $2 | $12 |
118
118
  | `kilo/google/gemini-3-pro-image-preview` | 66K | | | | | | $2 | $12 |
119
119
  | `kilo/google/gemini-3.1-flash-image` | 131K | | | | | | $0.50 | $3 |
120
120
  | `kilo/google/gemini-3.1-flash-image-preview` | 66K | | | | | | $0.50 | $3 |
@@ -131,19 +131,15 @@ for await (const chunk of stream) {
131
131
  | `kilo/google/gemma-3-12b-it` | 131K | | | | | | $0.05 | $0.15 |
132
132
  | `kilo/google/gemma-3-27b-it` | 131K | | | | | | $0.08 | $0.16 |
133
133
  | `kilo/google/gemma-3-4b-it` | 131K | | | | | | $0.05 | $0.10 |
134
- | `kilo/google/gemma-3n-e4b-it` | 33K | | | | | | $0.06 | $0.12 |
135
- | `kilo/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.05 | $0.25 |
136
- | `kilo/google/gemma-4-31b-it` | 262K | | | | | | $0.08 | $0.35 |
134
+ | `kilo/google/gemma-4-26b-a4b-it` | 262K | | | | | | $0.04 | $0.22 |
135
+ | `kilo/google/gemma-4-31b-it` | 262K | | | | | | $0.09 | $0.34 |
137
136
  | `kilo/google/lyria-3-clip-preview` | 1.0M | | | | | | — | — |
138
137
  | `kilo/google/lyria-3-pro-preview` | 1.0M | | | | | | — | — |
139
138
  | `kilo/gryphe/mythomax-l2-13b` | 4K | | | | | | $0.06 | $0.06 |
140
139
  | `kilo/ibm-granite/granite-4.0-h-micro` | 131K | | | | | | $0.02 | $0.11 |
141
140
  | `kilo/ibm-granite/granite-4.1-8b` | 131K | | | | | | $0.05 | $0.10 |
142
141
  | `kilo/inception/mercury-2` | 128K | | | | | | $0.25 | $0.75 |
143
- | `kilo/inclusionai/ling-2.6-1t` | 262K | | | | | | $0.30 | $3 |
144
- | `kilo/inclusionai/ling-2.6-flash` | 262K | | | | | | $0.10 | $0.30 |
145
142
  | `kilo/inclusionai/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
146
- | `kilo/inclusionai/ring-2.6-1t` | 262K | | | | | | $0.30 | $3 |
147
143
  | `kilo/kilo-auto/balanced` | 1.0M | | | | | | $0.33 | $2 |
148
144
  | `kilo/kilo-auto/efficient` | 1.0M | | | | | | $0.33 | $2 |
149
145
  | `kilo/kilo-auto/free` | 256K | | | | | | — | — |
@@ -160,9 +156,9 @@ for await (const chunk of stream) {
160
156
  | `kilo/meta-llama/llama-3.1-8b-instruct` | 131K | | | | | | $0.02 | $0.04 |
161
157
  | `kilo/meta-llama/llama-3.2-1b-instruct` | 60K | | | | | | $0.03 | $0.20 |
162
158
  | `kilo/meta-llama/llama-3.2-3b-instruct` | 131K | | | | | | $0.05 | $0.33 |
163
- | `kilo/meta-llama/llama-3.3-70b-instruct` | 131K | | | | | | $0.10 | $0.32 |
159
+ | `kilo/meta-llama/llama-3.3-70b-instruct` | 128K | | | | | | $0.10 | $0.32 |
164
160
  | `kilo/meta-llama/llama-4-maverick` | 1.0M | | | | | | $0.20 | $0.70 |
165
- | `kilo/meta-llama/llama-4-scout` | 328K | | | | | | $0.10 | $0.30 |
161
+ | `kilo/meta-llama/llama-4-scout` | 131K | | | | | | $0.10 | $0.30 |
166
162
  | `kilo/meta-llama/llama-guard-4-12b` | 164K | | | | | | $0.18 | $0.18 |
167
163
  | `kilo/meta/muse-glimmer-30b` | 131K | | | | | | $0.30 | $1 |
168
164
  | `kilo/meta/muse-spark-1.1` | 1.0M | | | | | | $1 | $4 |
@@ -175,10 +171,13 @@ for await (const chunk of stream) {
175
171
  | `kilo/minimax/minimax-m2` | 205K | | | | | | $0.30 | $1 |
176
172
  | `kilo/minimax/minimax-m2-her` | 66K | | | | | | $0.30 | $1 |
177
173
  | `kilo/minimax/minimax-m2.1` | 205K | | | | | | $0.30 | $1 |
178
- | `kilo/minimax/minimax-m2.5` | 198K | | | | | | $0.30 | $1 |
174
+ | `kilo/minimax/minimax-m2.5` | 200K | | | | | | $0.30 | $1 |
179
175
  | `kilo/minimax/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
176
+ | `kilo/minimax/minimax-m2.7:free` | 197K | | | | | | — | — |
180
177
  | `kilo/minimax/minimax-m3` | 524K | | | | | | $0.30 | $1 |
178
+ | `kilo/minimax/minimax-m3:free` | 1.0M | | | | | | — | — |
181
179
  | `kilo/mistralai/codestral-2508` | 256K | | | | | | $0.30 | $0.90 |
180
+ | `kilo/mistralai/devstral-2512` | 262K | | | | | | $0.44 | $2 |
182
181
  | `kilo/mistralai/ministral-14b-2512` | 262K | | | | | | $0.20 | $0.20 |
183
182
  | `kilo/mistralai/ministral-3b-2512` | 131K | | | | | | $0.10 | $0.10 |
184
183
  | `kilo/mistralai/ministral-8b` | 128K | | | | | | $0.11 | $0.11 |
@@ -189,12 +188,12 @@ for await (const chunk of stream) {
189
188
  | `kilo/mistralai/mistral-medium-3` | 131K | | | | | | $0.40 | $2 |
190
189
  | `kilo/mistralai/mistral-medium-3-5` | 262K | | | | | | $2 | $8 |
191
190
  | `kilo/mistralai/mistral-medium-3.1` | 131K | | | | | | $0.40 | $2 |
192
- | `kilo/mistralai/mistral-nemo` | 131K | | | | | | $0.02 | $0.03 |
191
+ | `kilo/mistralai/mistral-nemo` | 131K | | | | | | $0.17 | $0.17 |
193
192
  | `kilo/mistralai/mistral-saba` | 33K | | | | | | $0.20 | $0.60 |
194
193
  | `kilo/mistralai/mistral-small-24b-instruct-2501` | 33K | | | | | | $0.05 | $0.08 |
195
194
  | `kilo/mistralai/mistral-small-2603` | 262K | | | | | | $0.15 | $0.60 |
196
195
  | `kilo/mistralai/mistral-small-3.1-24b-instruct` | 128K | | | | | | $0.35 | $0.56 |
197
- | `kilo/mistralai/mistral-small-3.2-24b-instruct` | 128K | | | | | | $0.07 | $0.20 |
196
+ | `kilo/mistralai/mistral-small-3.2-24b-instruct` | 128K | | | | | | $0.11 | $0.33 |
198
197
  | `kilo/mistralai/mixtral-8x22b-instruct` | 66K | | | | | | $2 | $6 |
199
198
  | `kilo/mistralai/voxtral-small-24b-2507` | 32K | | | | | | $0.10 | $0.30 |
200
199
  | `kilo/moonshotai/kimi-k2` | 131K | | | | | | $0.57 | $2 |
@@ -270,7 +269,7 @@ for await (const chunk of stream) {
270
269
  | `kilo/openai/gpt-audio-mini` | 128K | | | | | | $0.60 | $2 |
271
270
  | `kilo/openai/gpt-chat-latest` | 400K | | | | | | $5 | $30 |
272
271
  | `kilo/openai/gpt-oss-120b` | 131K | | | | | | $0.03 | $0.17 |
273
- | `kilo/openai/gpt-oss-20b` | 131K | | | | | | $0.03 | $0.13 |
272
+ | `kilo/openai/gpt-oss-20b` | 131K | | | | | | $0.02 | $0.10 |
274
273
  | `kilo/openai/gpt-oss-safeguard-20b` | 131K | | | | | | $0.07 | $0.30 |
275
274
  | `kilo/openai/o1` | 200K | | | | | | $15 | $60 |
276
275
  | `kilo/openai/o1-pro` | 200K | | | | | | $150 | $600 |
@@ -299,13 +298,12 @@ for await (const chunk of stream) {
299
298
  | `kilo/qwen/qwen-2.5-coder-32b-instruct` | 33K | | | | | | $0.66 | $1 |
300
299
  | `kilo/qwen/qwen-plus` | 1.0M | | | | | | $0.26 | $0.78 |
301
300
  | `kilo/qwen/qwen-plus-2025-07-28` | 1.0M | | | | | | $0.26 | $0.78 |
302
- | `kilo/qwen/qwen-plus-2025-07-28:thinking` | 1.0M | | | | | | $0.26 | $0.78 |
303
- | `kilo/qwen/qwen2.5-vl-72b-instruct` | 128K | | | | | | $0.80 | $1 |
301
+ | `kilo/qwen/qwen2.5-vl-72b-instruct` | 32K | | | | | | $0.25 | $0.75 |
304
302
  | `kilo/qwen/qwen3-14b` | 41K | | | | | | $0.23 | $0.91 |
305
303
  | `kilo/qwen/qwen3-235b-a22b` | 131K | | | | | | $0.46 | $2 |
306
304
  | `kilo/qwen/qwen3-235b-a22b-2507` | 262K | | | | | | $0.15 | $0.60 |
307
305
  | `kilo/qwen/qwen3-235b-a22b-thinking-2507` | 131K | | | | | | $0.23 | $2 |
308
- | `kilo/qwen/qwen3-30b-a3b` | 131K | | | | | | $0.13 | $0.52 |
306
+ | `kilo/qwen/qwen3-30b-a3b` | 41K | | | | | | $0.13 | $0.52 |
309
307
  | `kilo/qwen/qwen3-30b-a3b-instruct-2507` | 128K | | | | | | $0.13 | $0.52 |
310
308
  | `kilo/qwen/qwen3-30b-a3b-thinking-2507` | 82K | | | | | | $0.20 | $2 |
311
309
  | `kilo/qwen/qwen3-32b` | 41K | | | | | | $0.08 | $0.28 |
@@ -343,7 +341,7 @@ for await (const chunk of stream) {
343
341
  | `kilo/qwen/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
344
342
  | `kilo/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
345
343
  | `kilo/qwen/qwen3.8-2.4t-a95b` | 1.0M | | | | | | $2 | $6 |
346
- | `kilo/qwen/qwen3.8-27b` | 262K | | | | | | $0.57 | $3 |
344
+ | `kilo/qwen/qwen3.8-27b` | 1.0M | | | | | | $0.42 | $3 |
347
345
  | `kilo/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
348
346
  | `kilo/rekaai/reka-edge` | 16K | | | | | | $0.10 | $0.10 |
349
347
  | `kilo/rekaai/reka-flash-3` | 66K | | | | | | $0.10 | $0.20 |
@@ -366,17 +364,18 @@ for await (const chunk of stream) {
366
364
  | `kilo/tencent/hunyuan-a13b-instruct` | 131K | | | | | | $0.14 | $0.57 |
367
365
  | `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
368
366
  | `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
369
- | `kilo/tencent/hy3` | 262K | | | | | | $0.13 | $0.53 |
367
+ | `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
368
+ | `kilo/tencent/hy3` | 262K | | | | | | $0.14 | $0.58 |
370
369
  | `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
371
370
  | `kilo/tencent/hy3:free` | 262K | | | | | | — | — |
372
371
  | `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
373
372
  | `kilo/thedrummer/rocinante-12b` | 66K | | | | | | $0.25 | $0.50 |
374
373
  | `kilo/thedrummer/skyfall-36b-v2` | 33K | | | | | | $0.55 | $0.80 |
375
- | `kilo/thedrummer/unslopnemo-12b` | 1.0M | | | | | | $0.40 | $0.40 |
374
+ | `kilo/thedrummer/unslopnemo-12b` | 33K | | | | | | $0.40 | $0.40 |
376
375
  | `kilo/thinkingmachines/inkling` | 524K | | | | | | $0.95 | $4 |
377
376
  | `kilo/thinkingmachines/inkling-small` | 524K | | | | | | $0.45 | $1 |
378
- | `kilo/thinkingmachines/inkling-small:free` | 262K | | | | | | — | — |
379
- | `kilo/thinkingmachines/inkling:free` | 262K | | | | | | — | — |
377
+ | `kilo/thinkingmachines/inkling-small:free` | 1.0M | | | | | | — | — |
378
+ | `kilo/thinkingmachines/inkling:free` | 1.0M | | | | | | — | — |
380
379
  | `kilo/undi95/remm-slerp-l2-13b` | 6K | | | | | | $0.45 | $0.65 |
381
380
  | `kilo/upstage/solar-pro-3` | 131K | | | | | | $0.15 | $0.60 |
382
381
  | `kilo/upstage/solar-pro4` | 524K | | | | | | $0.30 | $1 |
@@ -398,7 +397,7 @@ for await (const chunk of stream) {
398
397
  | `kilo/z-ai/glm-4.7-flash` | 203K | | | | | | $0.06 | $0.40 |
399
398
  | `kilo/z-ai/glm-5` | 198K | | | | | | $0.60 | $2 |
400
399
  | `kilo/z-ai/glm-5-turbo` | 203K | | | | | | $1 | $4 |
401
- | `kilo/z-ai/glm-5.1` | 200K | | | | | | $1 | $4 |
400
+ | `kilo/z-ai/glm-5.1` | 203K | | | | | | $1 | $4 |
402
401
  | `kilo/z-ai/glm-5.2` | 1.0M | | | | | | $1 | $4 |
403
402
  | `kilo/z-ai/glm-5.3` | 1.0M | | | | | | $1 | $4 |
404
403
  | `kilo/z-ai/glm-5v-turbo` | 203K | | | | | | $1 | $4 |
package/.docs/models/providers/llmgateway-providers.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![LLM Gateway logo](https://models.dev/logos/llmgateway-providers.svg)LLM Gateway
4
4
 
5
- Access 369 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
5
+ Access 378 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [LLM Gateway documentation](https://llmgateway.io/docs).
8
8
 
@@ -48,14 +48,14 @@ for await (const chunk of stream) {
48
48
  | `llmgateway-providers/alibaba/qwen-plus` | 131K | | | | | | $0.40 | $1 |
49
49
  | `llmgateway-providers/alibaba/qwen-plus-latest` | 1.0M | | | | | | $0.40 | $1 |
50
50
  | `llmgateway-providers/alibaba/qwen3-coder-flash` | 1.0M | | | | | | $0.30 | $2 |
51
- | `llmgateway-providers/alibaba/qwen3-coder-plus` | 1.0M | | | | | | $6 | $60 |
52
- | `llmgateway-providers/alibaba/qwen3-max` | 256K | | | | | | $3 | $15 |
51
+ | `llmgateway-providers/alibaba/qwen3-coder-plus` | 1.0M | | | | | | $1 | $5 |
52
+ | `llmgateway-providers/alibaba/qwen3-max` | 256K | | | | | | $1 | $6 |
53
53
  | `llmgateway-providers/alibaba/qwen3-vl-flash` | 262K | | | | | | $0.05 | $0.40 |
54
54
  | `llmgateway-providers/alibaba/qwen3-vl-plus` | 262K | | | | | | $0.20 | $2 |
55
- | `llmgateway-providers/alibaba/qwen3.6-35b-a3b` | 262K | | | | | | $0.25 | $1 |
55
+ | `llmgateway-providers/alibaba/qwen3.6-35b-a3b` | 262K | | | | | | $0.38 | $2 |
56
56
  | `llmgateway-providers/alibaba/qwen3.6-flash` | 1.0M | | | | | | $0.25 | $2 |
57
57
  | `llmgateway-providers/alibaba/qwen3.6-max-preview` | 262K | | | | | | $1 | $8 |
58
- | `llmgateway-providers/alibaba/qwen3.6-plus` | 262K | | | | | | $0.50 | $3 |
58
+ | `llmgateway-providers/alibaba/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
59
59
  | `llmgateway-providers/alibaba/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
60
60
  | `llmgateway-providers/alibaba/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
61
61
  | `llmgateway-providers/alibaba/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
@@ -97,6 +97,12 @@ for await (const chunk of stream) {
97
97
  | `llmgateway-providers/azure-ai-foundry/grok-4-1-fast-non-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
98
98
  | `llmgateway-providers/azure-ai-foundry/grok-4-1-fast-reasoning` | 2.0M | | | | | | $0.20 | $0.50 |
99
99
  | `llmgateway-providers/azure-ai-foundry/grok-4-3` | 20K | | | | | | $1 | $3 |
100
+ | `llmgateway-providers/azure-anthropic/claude-fable-5` | 1.0M | | | | | | $10 | $50 |
101
+ | `llmgateway-providers/azure-anthropic/claude-opus-4-6` | 1.0M | | | | | | $5 | $25 |
102
+ | `llmgateway-providers/azure-anthropic/claude-opus-4-7` | 1.0M | | | | | | $5 | $25 |
103
+ | `llmgateway-providers/azure-anthropic/claude-opus-4-8` | 1.0M | | | | | | $5 | $25 |
104
+ | `llmgateway-providers/azure-anthropic/claude-opus-5` | 1.0M | | | | | | $5 | $25 |
105
+ | `llmgateway-providers/azure-anthropic/claude-sonnet-5` | 1.0M | | | | | | $2 | $10 |
100
106
  | `llmgateway-providers/azure/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
101
107
  | `llmgateway-providers/azure/gpt-4` | 8K | | | | | | $30 | $60 |
102
108
  | `llmgateway-providers/azure/gpt-4-turbo` | 128K | | | | | | $10 | $30 |
@@ -127,11 +133,12 @@ for await (const chunk of stream) {
127
133
  | `llmgateway-providers/azure/o3` | 200K | | | | | | $2 | $8 |
128
134
  | `llmgateway-providers/azure/o3-mini` | 200K | | | | | | $1 | $4 |
129
135
  | `llmgateway-providers/azure/o4-mini` | 200K | | | | | | $1 | $4 |
130
- | `llmgateway-providers/baidu/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
131
- | `llmgateway-providers/baidu/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
136
+ | `llmgateway-providers/baidu/deepseek-v4-flash` | 1.0M | | | | | | $0.44 | $1 |
137
+ | `llmgateway-providers/baidu/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
132
138
  | `llmgateway-providers/baidu/glm-5` | 203K | | | | | | $1 | $3 |
133
139
  | `llmgateway-providers/baidu/glm-5.1` | 203K | | | | | | $1 | $4 |
134
140
  | `llmgateway-providers/baidu/glm-5.2` | 1.0M | | | | | | $1 | $4 |
141
+ | `llmgateway-providers/baidu/glm-5.3` | 1.0M | | | | | | $1 | $4 |
135
142
  | `llmgateway-providers/baidu/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
136
143
  | `llmgateway-providers/bytedance/deepseek-v3.2` | 131K | | | | | | $0.28 | $0.42 |
137
144
  | `llmgateway-providers/bytedance/deepseek-v4-flash` | 1.0M | | | | | | $0.44 | $1 |
@@ -162,6 +169,8 @@ for await (const chunk of stream) {
162
169
  | `llmgateway-providers/deepinfra/hy3` | 262K | | | | | | $0.14 | $0.58 |
163
170
  | `llmgateway-providers/deepinfra/kimi-k2.5` | 256K | | | | | | $0.45 | $2 |
164
171
  | `llmgateway-providers/deepinfra/ling-3.0-flash` | 262K | | | | | | $0.06 | $0.18 |
172
+ | `llmgateway-providers/deepinfra/mimo-v2.5` | 262K | | | | | | $0.40 | $2 |
173
+ | `llmgateway-providers/deepinfra/mimo-v2.5-pro` | 1.0M | | | | | | $1 | $3 |
165
174
  | `llmgateway-providers/deepinfra/nemotron-3-ultra-550b` | 262K | | | | | | $0.50 | $2 |
166
175
  | `llmgateway-providers/deepinfra/qwen3-vl-235b-a22b-instruct` | 262K | | | | | | $0.20 | $0.88 |
167
176
  | `llmgateway-providers/deepinfra/qwen3-vl-30b-a3b-instruct` | 262K | | | | | | $0.15 | $0.60 |
@@ -283,6 +292,8 @@ for await (const chunk of stream) {
283
292
  | `llmgateway-providers/novita/llama-3.3-70b-instruct` | 131K | | | | | | $0.14 | $0.40 |
284
293
  | `llmgateway-providers/novita/llama-4-maverick-17b-instruct` | 1.0M | | | | | | $0.27 | $0.85 |
285
294
  | `llmgateway-providers/novita/llama-4-scout-17b-instruct` | 131K | | | | | | $0.18 | $0.59 |
295
+ | `llmgateway-providers/novita/mimo-v2.5` | 1.0M | | | | | | $0.17 | $0.34 |
296
+ | `llmgateway-providers/novita/mimo-v2.5-pro` | 1.0M | | | | | | $0.52 | $1 |
286
297
  | `llmgateway-providers/novita/minimax-m2.1` | 205K | | | | | | $0.30 | $1 |
287
298
  | `llmgateway-providers/novita/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
288
299
  | `llmgateway-providers/novita/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
@@ -308,9 +319,7 @@ for await (const chunk of stream) {
308
319
  | `llmgateway-providers/openai/gpt-4.1-nano` | 1.0M | | | | | | $0.10 | $0.40 |
309
320
  | `llmgateway-providers/openai/gpt-4o` | 128K | | | | | | $3 | $10 |
310
321
  | `llmgateway-providers/openai/gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
311
- | `llmgateway-providers/openai/gpt-4o-mini-search-preview` | 128K | | | | | | $0.15 | $0.60 |
312
322
  | `llmgateway-providers/openai/gpt-4o-mini-transcribe` | 16K | | | | | | $1 | $5 |
313
- | `llmgateway-providers/openai/gpt-4o-search-preview` | 128K | | | | | | $3 | $10 |
314
323
  | `llmgateway-providers/openai/gpt-4o-transcribe` | 16K | | | | | | $3 | $10 |
315
324
  | `llmgateway-providers/openai/gpt-5` | 400K | | | | | | $1 | $10 |
316
325
  | `llmgateway-providers/openai/gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
package/.docs/models/providers/llmgateway.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![DevPass (LLM Gateway) logo](https://models.dev/logos/llmgateway.svg)DevPass (LLM Gateway)
4
4
 
5
- Access 189 DevPass (LLM Gateway) models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
5
+ Access 187 DevPass (LLM Gateway) models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [DevPass (LLM Gateway) documentation](https://llmgateway.io/docs).
8
8
 
@@ -97,9 +97,7 @@ for await (const chunk of stream) {
97
97
  | `llmgateway/gpt-4.1-nano` | 1.0M | | | | | | $0.10 | $0.40 |
98
98
  | `llmgateway/gpt-4o` | 128K | | | | | | $3 | $10 |
99
99
  | `llmgateway/gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
100
- | `llmgateway/gpt-4o-mini-search-preview` | 128K | | | | | | $0.15 | $0.60 |
101
100
  | `llmgateway/gpt-4o-mini-transcribe` | 16K | | | | | | $1 | $5 |
102
- | `llmgateway/gpt-4o-search-preview` | 128K | | | | | | $3 | $10 |
103
101
  | `llmgateway/gpt-4o-transcribe` | 16K | | | | | | $3 | $10 |
104
102
  | `llmgateway/gpt-5` | 400K | | | | | | $1 | $10 |
105
103
  | `llmgateway/gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
@@ -198,7 +196,7 @@ for await (const chunk of stream) {
198
196
  | `llmgateway/qwen3-coder-480b-a35b-instruct` | 262K | | | | | | $0.38 | $2 |
199
197
  | `llmgateway/qwen3-coder-flash` | 1.0M | | | | | | $0.30 | $2 |
200
198
  | `llmgateway/qwen3-coder-next` | 262K | | | | | | $0.11 | $0.68 |
201
- | `llmgateway/qwen3-coder-plus` | 1.0M | | | | | | $6 | $60 |
199
+ | `llmgateway/qwen3-coder-plus` | 1.0M | | | | | | $1 | $5 |
202
200
  | `llmgateway/qwen3-max` | 262K | | | | | | $0.84 | $3 |
203
201
  | `llmgateway/qwen3-next-80b-a3b-instruct` | 131K | | | | | | $0.15 | $1 |
204
202
  | `llmgateway/qwen3-next-80b-a3b-thinking` | 131K | | | | | | $0.15 | $1 |
@@ -211,7 +209,7 @@ for await (const chunk of stream) {
211
209
  | `llmgateway/qwen3.6-35b-a3b` | 262K | | | | | | $0.25 | $1 |
212
210
  | `llmgateway/qwen3.6-flash` | 1.0M | | | | | | $0.25 | $2 |
213
211
  | `llmgateway/qwen3.6-max-preview` | 262K | | | | | | $1 | $8 |
214
- | `llmgateway/qwen3.6-plus` | 262K | | | | | | $0.50 | $3 |
212
+ | `llmgateway/qwen3.6-plus` | 1.0M | | | | | | $0.50 | $3 |
215
213
  | `llmgateway/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
216
214
  | `llmgateway/qwen3.7-max` | 1.0M | | | | | | $1 | $4 |
217
215
  | `llmgateway/qwen3.7-plus` | 1.0M | | | | | | $0.40 | $2 |
package/.docs/models/providers/llmtech.md ADDED
@@ -0,0 +1,73 @@
1
+ > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
2
+
3
+ # ![LLM Tech logo](https://models.dev/logos/llmtech.svg)LLM Tech
4
+
5
+ Access 1 LLM Tech model through Mastra's model router. Authentication is handled automatically using the `LLMTECH_API_KEY` environment variable.
6
+
7
+ Learn more in the [LLM Tech documentation](https://llmtech.eu/models/qwen3.8-27b).
8
+
9
+ ```bash
10
+ LLMTECH_API_KEY=your-api-key
11
+ ```
12
+
13
+ ```typescript
14
+ import { Agent } from "@mastra/core/agent";
15
+
16
+ const agent = new Agent({
17
+ id: "my-agent",
18
+ name: "My Agent",
19
+ instructions: "You are a helpful assistant",
20
+ model: "llmtech/unsloth/Qwen3.8-27B-NVFP4"
21
+ });
22
+
23
+ // Generate a response
24
+ const response = await agent.generate("Hello!");
25
+
26
+ // Stream a response
27
+ const stream = await agent.stream("Tell me a story");
28
+ for await (const chunk of stream) {
29
+ console.log(chunk);
30
+ }
31
+ ```
32
+
33
+ > **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [LLM Tech documentation](https://llmtech.eu/models/qwen3.8-27b) for details.
34
+
35
+ ## Models
36
+
37
+ | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
+ | ----------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
+ | `llmtech/unsloth/Qwen3.8-27B-NVFP4` | 262K | | | | | | $0.25 | $2 |
40
+
41
+ ## Advanced configuration
42
+
43
+ ### Custom headers
44
+
45
+ ```typescript
46
+ const agent = new Agent({
47
+ id: "custom-agent",
48
+ name: "custom-agent",
49
+ model: {
50
+ url: "https://api.llmtech.eu/v1",
51
+ id: "llmtech/unsloth/Qwen3.8-27B-NVFP4",
52
+ apiKey: process.env.LLMTECH_API_KEY,
53
+ headers: {
54
+ "X-Custom-Header": "value"
55
+ }
56
+ }
57
+ });
58
+ ```
59
+
60
+ ### Dynamic model selection
61
+
62
+ ```typescript
63
+ const agent = new Agent({
64
+ id: "dynamic-agent",
65
+ name: "Dynamic Agent",
66
+ model: ({ requestContext }) => {
67
+ const useAdvanced = requestContext.task === "complex";
68
+ return useAdvanced
69
+ ? "llmtech/unsloth/Qwen3.8-27B-NVFP4"
70
+ : "llmtech/unsloth/Qwen3.8-27B-NVFP4";
71
+ }
72
+ });
73
+ ```